Delete a memento and all its relationships
AI agents call delete_memento to permanently remove resources in MCP Memento — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
This tool permanently removes data (a memento and associated relationships) from the knowledge base without the ability to undo the action. Deletion is irreversible and represents data loss. While the blast radius is scoped to individual mementos rather than the entire database, the permanent nature of deletion and loss of stored solutions/facts/decisions classifies this as Destructive.
From the tool's definition Tool name is 'delete_memento' and description states 'Delete a memento and all its relationships' — explicit deletion language with irreversible effects.
Attacks that exploit this kind of access
Delete a memento and all its relationships. It is categorised as a Destructive tool in the MCP Memento MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the MCP Memento MCP server in PolicyLayer and add a rule for delete_memento: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches MCP Memento. Nothing to install.
delete_memento is a Destructive tool with critical risk. Critical-risk tools should be blocked by default and only enabled with explicit human approval.
Yes. Add a rate_limit block to the delete_memento rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.
Set action: deny in the PolicyLayer policy for delete_memento. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.
delete_memento is provided by the MCP Memento MCP server (x-hannibal/mcp-memento). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →